Predicted protein shapes guide a search for new drug leads

UCSF-led teams docked up to 1.6 billion molecules against AlphaFold2 models of the sigma-2 and 5-HT2A receptors; hit rates (54% and 26%) matched those from experimental structures.

2
Benefit status
Reported
Evidence
Claimed by the parties
Source published
Sources
1 publication
Download data CiteSuggest a correction

Benefits

Benefit

A hit rate of 54%, against 51% for the crystal structure

Awaiting review

Outcome identifiers

Unresolved

Not reviewedUnresolved

Category

Improved Knowledge Discovery

Awaiting review

Status

Reported benefit

Awaiting review

Beneficiary groups

Society.

Awaiting review

Beneficiaries

Unresolved

Not reviewedUnresolved

Reach

Unresolved

Not reviewedUnresolved

Distribution and access

Unresolved

Not reviewedUnresolved

Duration

Unresolved

Not reviewedUnresolved

Expected?

No

Awaiting review

Costs and harms

Unresolved

Not reviewedUnresolved

AI system

System

AlphaFold2 (AF2) predicted structures used for large-library docking

Awaiting review

Model

This is an explicit unresolved assignment: the sources on record do not settle this question.

Not reviewedUnresolved

Release

Unresolved

Not reviewedUnresolved

Provider

Unresolved

Not reviewedUnresolved

Role

Unresolved

Not reviewedUnresolved

Configuration

Unresolved

Not reviewedUnresolved

Inputs and outputs

Unresolved

Not reviewedUnresolved

Autonomy

Unresolved

Not reviewedUnresolved

Workflow

The AlphaFold2 models were predicted before the experimental structures were released. Hundreds of top-ranked molecules were synthesized and tested for each structure.

Awaiting review

Human oversight

Unresolved

Not reviewedUnresolved

Relation to AI

The authors ran the same libraries and docking pipeline against the AlphaFold2 model and the experimental structure of each receptor, so they isolate the contribution of the predicted structure.

Awaiting review

AI contribution

The authors ran the same libraries and docking pipeline against the AlphaFold2 model and the experimental structure of each receptor, so they isolate the contribution of the predicted structure.

Awaiting review

Measurement

Studies

Controlled observational. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Study design

Controlled observational. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Measurement

Radioligand binding assays of docked molecules; hit rate and affinity. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Setting and sample

About 500 synthesized molecules from docking 490 million (sigma-2) and 1.6 billion (5-HT2A) molecules. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Measures

Hit rate (actives per molecules tested) and affinity. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Comparison

Docking against experimental crystal and cryo-EM structures. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Results

54% against 51% (sigma-2); 26% against 23% (5-HT2A); not significantly different. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Additional value from AI

Predicted structures matched experimental ones for ligand discovery. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Limitations

Two receptors; functional hit rates for 5-HT2A were 1 to 5%; retrospective enrichment favored experimental structures. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Denominators

Docking campaigns at UCSF; assays at UNC and elsewhere. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Materials for replication

Models, docking results and compounds described in the supplement; ZINC library public. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Money

Kind of value

The kind of monetary value is unclear.

Not reviewedUnresolved

Amount

The monetary value is not established.

Not reviewedUnresolved

Currency and prices

The currency and price basis are unclear.

Not reviewedUnresolved

Period and unit

The period and unit of the monetary estimate are unclear.

Not reviewedUnresolved

Realization

Whether the monetary value was realized is unclear.

Not reviewedUnresolved

Recipients and payers

The recipients and payers are unclear.

Not reviewedUnresolved

Gross or net

Whether the monetary figure includes costs is unclear.

Not reviewedUnresolved

Included costs

The costs included in the estimate are unclear.

Not reviewedUnresolved

Comparison

The financial comparison is not established.

Not reviewedUnresolved

Method

The method used to calculate monetary value is unclear.

Not reviewedUnresolved

Return and payback

The return on investment or payback period is not established.

Not reviewedUnresolved

People and places

Participants

Developer: DeepMind. Operator: University of California, San Francisco (Shoichet and Irwin laboratories) with the University of North Carolina at Chapel Hill (Roth laboratory), Stanford University and Harvard Medical School.

Awaiting review

Jurisdictions

Benefit: San Francisco and Stanford, California; Chapel Hill, North Carolina; Boston, Massachusetts; New York, New York, United States. Developer: United Kingdom. Operator: United States.

Awaiting review

Ownership and control

Unresolved

Not reviewedUnresolved

Dependencies

Unresolved

Not reviewedUnresolved

Cross-border connections

Unresolved

Not reviewedUnresolved

Geopolitical implications

The geopolitical implications are unclear.

Not reviewedUnresolved

Follow-up

Conditions for replication

The binding pocket must be predicted with good accuracy. Large make-on-demand libraries and binding assays must be available.

Awaiting review

Replication attempts

1 follow-up entry. Benefit recurred: 1.

Awaiting review

Later findings

Unresolved

Not reviewedUnresolved

Availability

Unresolved

Not reviewedUnresolved

Institutional decision

A relevant institutional decision has not been established.

Not reviewedUnresolved

Grounds

The grounds for an institutional decision are unclear.

Not reviewedUnresolved

Action and result

The result of an institutional decision is not established.

Not reviewedUnresolved

Success criterion

The criterion for a successful institutional decision is unclear.

Not reviewedUnresolved

Evidence

Source numbers

AIBD-0658-source-0001

Awaiting review

Citations

Numbered references below.

Awaiting review

Language

Unresolved

Not reviewedUnresolved

Source relationships

Operator

Awaiting review

Original evidence

Unresolved

Not reviewedUnresolved

Access and versions

Unresolved

Not reviewedUnresolved

Supported findings

Unresolved

Not reviewedUnresolved

Evidence strength

The deployer's account. Sources: the deployer's peer-reviewed study. The cited evidence includes no independent source and no finding by a regulator or court. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Missing evidence

Unresolved

Not reviewedUnresolved

Grades

Assessed benefits

Society.

Awaiting review

Depth

Society: 2.

Awaiting review

Reasons

Society: The screens produced new sigma-2 and 5-HT2A ligands at hit rates equal to those from experimental structures (54% and 26%).

Awaiting review

Observed or intended

Unresolved

Not reviewedUnresolved

Rubric

Unresolved

Not reviewedUnresolved

Assessor and date

Unresolved

Not reviewedUnresolved

Alternative assessments

Unresolved

Not reviewedUnresolved

Fill

The deployer's account

Awaiting review

Entry details

Kind

The case describes an evaluation or a study. A head-to-head prospective comparison of predicted and experimental structures. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Field

Drug discovery.

Awaiting review

Purpose

AlphaFold2 was built to predict protein structures. Use of the predicted structures for ligand discovery is an application by independent researchers.

Awaiting review

Dates

Source published: 21 June 2024. Updated: 29 October 2026.

Awaiting review

Stage

The system was tested in a laboratory. Prospective docking and laboratory binding assays. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Version

SHA-256: 868371375049…

Awaiting review

SHA-256 of the public case, its assessments, and its displayed answers and notes, excluding its own identifier and the derived coverage summary.

References

Other identifiers

Unresolved

Not reviewedUnresolved

Category mappings

Unresolved

Not reviewedUnresolved

Citable summary

Unresolved

Not reviewedUnresolved

Revisions

1 revision. Latest: 29 October 2026.

Awaiting review

Sources

  1. Peer-reviewed study Deployer

    Lyu J, Kapolka N, Gumpper R, et al. AlphaFold2 structures guide prospective ligand discovery. Science. 2024;384(6702):eadn6354.

Collections: Cross-border cases.

Cite this case

BibTeX Download BibTeX

Version 868371375049, archived in the edition of 29 October 2026

Benefit marks

Depth

The number and color show the depth of a benefit.

  1. A convenience, or time or money saved.
  2. A measurable improvement in a result or ability.
  3. A lasting change, an ability restored, or a risk removed.
  4. A serious harm averted or a serious condition resolved in time.
  5. A life or livelihood preserved, or a change documented across a population.

Beneficiary

  • Circle: a person
  • Square: an organization
  • Triangle: society

Evidence

  • Solid. A court or regulator found a benefit, or researchers independently studied it.

  • Hatched. Independent reporting.

  • Outline. Claimed by the parties. Only the people or organizations involved, or sources whose independence has not been assessed, support the benefit.

The fill changes with the evidence. The depth color stays the same.

How benefits are assessed